DOI QR코드

DOI QR Code

Deep Learning-Based, Real-Time, False-Pick Filter for an Onsite Earthquake Early Warning (EEW) System

온사이트 지진조기경보를 위한 딥러닝 기반 실시간 오탐지 제거

  • 서정범 (케이아이티밸리 AiLab) ;
  • 이진구 (케이아이티밸리 AiLab) ;
  • 이우동 (전북대학교 지구환경과학과) ;
  • 이석태 (케이아이티밸리 AiLab) ;
  • 이호준 (케이아이티밸리 연구기획본부) ;
  • 전인찬 (케이아이티밸리 AiLab) ;
  • 박남률 (케이아이티밸리 AiLab)
  • Received : 2020.12.31
  • Accepted : 2021.02.14
  • Published : 2021.03.01

Abstract

This paper presents a real-time, false-pick filter based on deep learning to reduce false alarms of an onsite Earthquake Early Warning (EEW) system. Most onsite EEW systems use P-wave to predict S-wave. Therefore, it is essential to properly distinguish P-waves from noises or other seismic phases to avoid false alarms. To reduce false-picks causing false alarms, this study made the EEWNet Part 1 'False-Pick Filter' model based on Convolutional Neural Network (CNN). Specifically, it modified the Pick_FP (Lomax et al.) to generate input data such as the amplitude, velocity, and displacement of three components from 2 seconds ahead and 2 seconds after the P-wave arrival following one-second time steps. This model extracts log-mel power spectrum features from this input data, then classifies P-waves and others using these features. The dataset consisted of 3,189,583 samples: 81,394 samples from event data (727 events in the Korean Peninsula, 103 teleseismic events, and 1,734 events in Taiwan) and 3,108,189 samples from continuous data (recorded by seismic stations in South Korea for 27 months from 2018 to 2020). This model was trained with 1,826,357 samples through balancing, then tested on continuous data samples of the year 2019, filtering more than 99% of strong false-picks that could trigger false alarms. This model was developed as a module for USGS Earthworm and is written in C language to operate with minimal computing resources.

Keywords

References

  1. Jeon YS, Park EH, Lee DK. 9.12 Earthquake Response Report. Korea Meteorological Administration. 2017. 28 p.
  2. Bebbington M, Harte D. The linked stress release model for spatiotemporal seismicity: formulations, procedures and applications. Geophysical Journal International. 2003 Sep;154(3):925-946. https://doi.org/10.1046/j.1365-246X.2003.02015.x
  3. Pritchard ME, Allen RM, Becker TW, Behn MD, Brodsky EE, Burgmann R, Ebinger C, Freymueller JT, Gerstenberger M, Haines B, Kaneko Y, Jacobsen SD, Lindsey N, McGuire JJ, Page M, Ruiz S, Tolstoy M, Wallace L, Walter WR, Wilcock W, Vincent H. New Opportunities to Study Earthquake Precursors. Seismological Research Letters. 2020 JUL;91(5):2444-2447. https://doi.org/10.1785/0220200089
  4. Allen MR. Kanamori H, The Potential for Earthquake Early Warning in Southern California. Science. 2003 May;300(5620):768-789.
  5. Allen RM, Melgar D. Earthquake Early Warning: Advances, Scientific Challenges, and Societal Needs. Annual Review of Earth and Planetary Sciences. 2019 May;47:361-388. https://doi.org/10.1146/annurev-earth-053018-060457
  6. Allen RM. Probabilistic warning times for earthquake ground shaking in the San Francisco Bay Area. Seismological Research Letters. 2006;77(3):371-376. https://doi.org/10.1785/gssrl.77.3.371
  7. Hoshiba M, Iwakiri K, Hayashimoto N, Shimoyama T, Hirano K, Yamada Y, et al. Outline of the 2011 off the Pacific coast of Tohoku Earthquake (Mw 9.0)-Earthquake Early Warning and observed seismic intensity. Earth, Planets and Space. 2011 May;63(7).
  8. Cochran ES, Kohler MD, Given DD, Guiwits S, Andrews J, Meier MA, et al. Earthquake early warning ShakeAlertsystem: Testing and certi cation platform. Seismological Research Letters. 2018;89(1):108-117. https://doi.org/10.1785/0220170138
  9. Meier MA, Ross ZE, Ramachandran A, Balakrishna A, Nair S, Kundzicz P, et al. Reliable Real Time Seismic Signal/Noise Discrimination With Machine Learning. Journal of Geophysical Research: Solid Earth, 2019;124:788-800. https://doi.org/10.1029/2018jb016661
  10. Meier MA, Kodera Y, BBse M, Chung A, Hoshiba M, Cochran E, et al. How often can Earthquake Early Warning systems alert sites with high intensity ground motion?. Journal of Geophysical Research: Solid Earth. c2020.
  11. Chung A, Henson I, Allen RM. Optimizing Earthquake Early Warning Performance: ElarmS-3. Seismological Research Letters. 2019;90(2A):727-743. https://doi.org/10.1785/0220180192
  12. Seo JB, Lee JK, Jeon I, Cho KC, Park NR, Lee ST, Ko HW, Jeong H, Lee JH, Jang GR, Lee JK, Kang JW, Cho CK, Lee JW, Park DK, Lee SK, Kang HR, Lee HK, Kim MC, Kang CS, Choi YJ. A Development of Base for Earthquake Early Warning 2nd Step Service (III). Korea Meteorological Administration. c2018.
  13. Caruso A, Colombelli S, Elia L, Picozzi M, Zollo A. An on-site alert level early warning system for Italy: An onsite early warning system for Italy. Journal of Geophysical Research: Solid Earth. c2017.
  14. Wu YM, Kanamori H. Experiment on an Onsite Early Warning Method for the Taiwan Early Warning System. Bulletin of the Seismological Society of America. 2005;95(1):347-353. https://doi.org/10.1785/0120040097
  15. Lomax A, Satriano C, Vassallo M. Automatic Picker Developments and Optimization: FilterPicker-a Robust, Broadband Picker for Real-Time Seismic Monitoring and Earthquake Early Warning. Seismological Research Letters. 2012;83:531-540. https://doi.org/10.1785/gssrl.83.3.531
  16. Vassallo M, Satriano C, Lomax A, Automatic Picker Developments and Optimization: A Strategy for Improving the Performances of Automatic Phase Pickers. Seismological Research Letters. 2012;83(3):541-554. https://doi.org/10.1785/gssrl.83.3.541
  17. Lee HJ, Jeon I, Seo JB, Lee JK. Application of the onsite EEW technology using the P-wave of seismic records in Korea. Journal of the Society of Disaster Information. 2020;16(1):133-143. https://doi.org/10.15683/KOSDI.2020.3.31.133
  18. Seo JB. Introduction to the production procedures and technologies of KMA intensity information. Korea Meteorological Administration. 2019 Apr:56-59.
  19. Samuel AL. Some studies in machine learning using the game of checkers. IBM Journal of Research and Development. 1959;3(3):210-229. https://doi.org/10.1147/rd.33.0210
  20. Perol T, Gharbi M, Denolle M. Convolutional neural network for earthquake detection and location. Science Advances. 2018 Feb;4(2).
  21. Wang B, Zhang N, Lu W, Wang J. Deep-learning-based seismic data interpolation: A preliminary result. GEOPHYSICS. 2019 Jan;84(1):1JF-Z5. https://doi.org/10.1190/geo2018-1220-tiogeo.1
  22. Derakhshani A, Foruzan AH. Predicting the principal strong ground motion parameters: A deep learning approach. Applied Soft Computing. 2019 Jul;80:192-201. https://doi.org/10.1016/j.asoc.2019.03.029
  23. Seydoux L, Balestriero R, Poli P, Hoop M, Campillo M, Baraniuk R. Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning. Nat Commun. 2020 Aug;11:3972. https://doi.org/10.1038/s41467-020-17841-x
  24. Araya-Polo M, Jennings J, Adler A, Dahlke T. Deep-learning tomography. The Leading Edge. 2018 Jan;37(1):2-80.
  25. Kong Q, Chai C, Li Z, Chen M, Wang R. 2018 Seismology of the Americas Meeting:Technical Sessions:Applications of Machine Learning and Data Science in Seismology. Seismological Research Letters. 2018 Mar-Apr;89(2B):728-729.
  26. Hsu TY, Wang HH, Lin PY, Lin CM, Kuo CH, We KL. Performance of the NCREE's on-site warning system during the 5 February 2016 Mw 6.53 Meinong earthquake. Geophysical Research Letters. 2016 Aug;43(17).
  27. Choi YS. Earthquake prediction and warning in 5 seconds by artificial intelligence... AI earthquake early warning system released in Taiwan. [Internet]. IT Chosun. 2018 Jan. Available from; http://it.chosun.com/site/data/html_dir/2018/01/01/2018010185010.html.
  28. Ross ZE, Meier MA, Hauksson E, Heaton TH. Generalized Seismic Phase Detection with Deep Learning. Bulletin of the Seismological Society of America. 2019 Jan;108(5A):2894-2901.
  29. Ronneberger 0, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Miccai. 2015:234-241.
  30. Zhu W, Beroza GC. PhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method. arXiv:1803.03211v1 [physics.geo-ph]. c2018. https://doi.org/10.1093/gji/ggy423
  31. Kim SI, Kim DH, Shin HH, Ku BH, Ko H. Earthquake detection based on convolutional neural network using multi-band frequency signals. 2019;38(1):23-29. https://doi.org/10.7776/ASK.2019.38.1.023
  32. Geron A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition. O'Reilly Media, Inc.; c2019.
  33. Seo JB, Lee JK, Jeon I, Lee HJ. Development of Onsite warning technology using Deep Learning. Proceedings of EESK Conference 2020. 2020 Sep;7-8.
  34. Kennett BLN, Engdahl ER. Travel times for global earthquake location and phase association. Geophysical Journal International. 1991;105:429-465. https://doi.org/10.1111/j.1365-246X.1991.tb06724.x
  35. Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. c2016.
  36. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 25 (NIPS 2012). 2012:1097-1105.
  37. Allen RV. Automatic earthquake recognition and timing from single traces. Bulletin of the Seismological Society of America. 1978;68(5):1521-1532. https://doi.org/10.1785/BSSA0680051521
  38. Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. 27th International Conference on Machine Learning (ICML 2010). c2010.
  39. Srivastava N. Improving neural networks with dropout. Ph.D. thesis, University of Toronto. 2013.
  40. Goodfellow I, Bengio Y, Courville A, Deep Learning. MIT Press. c2016.
  41. Fernandez-Redondo M, Hernandez-Espinosa C. Weight initialization methods for multilayer feedforward. ESANN. 2001 Apr:119-124.
  42. Seo JB, Lee JK, Lee HJ, Jeon I, Lee J, Ahn JK, inventors; Method for determining real-time alarm for local target earthquake early warning using mechanical learning. Korean patent 10-2020-0147842.
  43. Volcano, Earthquake, Tsunami. Korea Meteorological Administration. [Internet]. Available from: https://www.weather.go.kr/download_01/disaster_book.pdf: 14 p.